language_models: Improve token counting for providers (#32853)

We push the usage data whenever we receive it from the provider to make
sure the counting is correct after the turn has ended.

- [x] Ollama 
- [x] Copilot 
- [x] Mistral 
- [x] OpenRouter 
- [x] LMStudio

Put all the changes into a single PR open to move these to separate PR
if that makes the review and testing easier.

Release Notes:

- N/A

crates/language_models/src/provider/mistral.rs

@@ -13,7 +13,7 @@ use language_model::{
     LanguageModelId, LanguageModelName, LanguageModelProvider, LanguageModelProviderId,
     LanguageModelProviderName, LanguageModelProviderState, LanguageModelRequest,
     LanguageModelToolChoice, LanguageModelToolResultContent, LanguageModelToolUse, MessageContent,
-    RateLimiter, Role, StopReason,
+    RateLimiter, Role, StopReason, TokenUsage,
 };
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
@@ -626,6 +626,15 @@ impl MistralEventMapper {
             }
         }
 
+        if let Some(usage) = event.usage {
+            events.push(Ok(LanguageModelCompletionEvent::UsageUpdate(TokenUsage {
+                input_tokens: usage.prompt_tokens,
+                output_tokens: usage.completion_tokens,
+                cache_creation_input_tokens: 0,
+                cache_read_input_tokens: 0,
+            })));
+        }
+
         if let Some(finish_reason) = choice.finish_reason.as_deref() {
             match finish_reason {
                 "stop" => {